111P Application of radiomics signatures and unidimensional vs volumetric measurement of early tumor growth dynamics (TGD) to predict first-line treatment outcomes in patients with stage IV non-small cell lung cancer (NSCLC)

TGD modeling using sum of longest diameters (SLD) is associated with long-term outcomes in NSCLC. Early changes radiomics features within the tumor may also correlate survival outcomes. We retrospectively evaluated 3 methods to assess early treatment outcomes: growth rate (g) by SLD, volumetric measurements, and change signatures predict Patients stage IV NSCLC CheckMate 9LA treated first-line nivolumab+ipilimumab+chemotherapy (NIVO+IPI+CHEMO) or CHEMO alone were included. was modeled radiologically-assessed SLD from ≤5 target lesions volumes (SVOL) all measurable >10 mm at baseline, 6, 12, and/or 18 weeks. Measurements fitted model. 1Fojo AT et al. J Clin Oncol. 2022;40(16_suppl):Abst 9063. Overall (OS) for each quartile estimated Kaplan–Meier curves. Changes radiomic assessed week 6 12. At 18, low SVOL- SLD-derived g values longer median OS across both arms. SVOL-derived more consistent timepoints if 12 than values. Delta (table) performed better RECIST 1.1 NIVO+IPI+CHEMO arm. Table 111PMedian groups defined unidimensional vs estimates growth, criteria response delta signatureMedian OS, monthsSLD measurementsaFour timepoints, 18. grouped according quartiles g, 1 representing subgroup slowest g.SVOL g.NIVO +IPI +CHEMOCHEMO aloneNIVO aloneg quartile1 g25.817.926.419.1quartile412.59.511.68.2Median monthsRECIST (NIVO IPI+CHEMO)Delta radiomics-derived (NIVO+IPI +CHEMO)At weeksAt weeksProgressive disease7.17.4Stable disease15.014.5Partial complete response32.54a Four g. Open table a new tab are weeks treatment. as on-treatment identifying patients deriving benefit. Both findings can potentially inform decision making clinical trials real-world use.